Neural networks are often quantized to use reduced-precision arithmetic, as it greatly improves their storage and computational costs. This approach is commonly used in image classification and natural language processing applications. However, using a quantized network for the reconstruction of HDR images can lead to a significant loss in image quality. In this paper, we introduce QW-Net , a neural network for image reconstruction, in which close to 95% of the computations can be implemented with 4-bit integers. This is achieved using a combination of two U-shaped networks that are specialized for different tasks, a feature extraction network based on the U-Net architecture, coupled to a filtering network that reconstructs the output image. The feature extraction network has more computational complexity but is more resilient to quantization errors. The filtering network, on the other hand, has significantly fewer computations but requires higher precision. Our network recurrently warps and accumulates previous frames using motion vectors, producing temporally stable results with significantly better quality than TAA, a widely used technique in current games.

中文翻译：

---

用于图像重建的降低精度网络

神经网络通常被量化以使用降低精度的算法，因为它大大提高了它们的存储和计算成本。这种方法通常用于图像分类和自然语言处理应用中。然而，使用量化网络重建 HDR 图像可能会导致图像质量的显着下降。在本文中，我们介绍量子网络，用于图像重建的神经网络，其中接近 95% 的计算可以用 4 位整数实现。这是通过结合两个专门用于不同任务的 U 形网络来实现的，一个特征提取基于 U-Net 架构的网络，耦合到过滤重建输出图像的网络。特征提取网络具有更高的计算复杂性，但对量化误差更具弹性。另一方面，过滤网络的计算量显着减少，但需要更高的精度。我们的网络使用运动向量反复扭曲和累积先前的帧，产生时间稳定的结果，其质量明显优于当前游戏中广泛使用的 TAA 技术。